Kunocchini-7b / README.md
Nitral
Update README.md
4369460 verified
|
raw
history blame
1.52 kB
metadata
base_model:
  - SanjiWatsuki/Kunoichi-DPO-v2-7B
  - Epiculous/Fett-uccine-7B
library_name: transformers
tags:
  - mergekit
  - merge
  - alpaca
  - mistral
license: other

Thanks to @Epiculous for the dope model/ help with llm backends and support overall.

Id like to also thank @kalomaze for the dope sampler additions to ST.

@SanjiWatsuki Thank you very much for the help, and the model!

ST users can find the TextGenPreset in the folder labeled so.

image/jpeg

Quants:Thank you @bartowski! https://huggingface.co/bartowski/Kunocchini-exl2 and @jeiku https://huggingface.co/jeiku/Konocchini-7B_GGUF Thanks to @konz00 for the additional GGUF Quants: https://huggingface.co/konz00/Kunocchini-7b-GGUF

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: SanjiWatsuki/Kunoichi-DPO-v2-7B
        layer_range: [0, 32]
      - model: Epiculous/Fett-uccine-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.5
dtype: bfloat16